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. 24-GEMMASCOPE-RES-16K
    6. 14063
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online resources

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

    Text within URLs or citations

    np_acts-logits-general · gemini-2.0-flash

    URLs and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.67
    出版年
    -0.58
    WithIOException
    -0.58
    lastIndexOf
    -0.53
     useEffect
    -0.52
    UserScript
    -0.52
    Diweddarwch
    -0.52
    غرب
    -0.51
    EDEFAULT
    -0.51
     Schlegel
    -0.50
    POSITIVE LOGITS
    InvalidProtocol
    0.53
    {
    0.53
     AUSSI
    0.53
    protoimpl
    0.52
    cleros
    0.50
     consultato
    0.48
     OGSÅ
    0.48
     rospy
    0.48
     linkovi
    0.47
    GOTREF
    0.46
    Activations Density 0.084%

    No Known Activations