Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5187
    Prev
    Next
    INDEX
    Explanations

    terms related to access or accessibility in technological contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    text related to technical systems and technology.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to accessing or gaining entry to systems, information, or resources.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    The token "access"

    np_acts-logits-general · gemini-2.0-flash

    access and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.65
    richTextPanel
    -0.60
    udadera
    -0.59
     surla
    -0.56
    mester
    -0.55
    openzeppelin
    -0.55
     tetrachloride
    -0.54
    thâu
    -0.53
    isserie
    -0.53
    انيف
    -0.53
    POSITIVE LOGITS
    ACCESS
    0.65
     BorderRadius
    0.64
    ChildScrollView
    0.63
     Denied
    0.62
     Egli
    0.61
    oris
    0.59
    Denied
    0.59
    oire
    0.58
     denied
    0.57
     Access
    0.56
    Activations Density 0.087%

    No Known Activations