© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9014
    Prev
    Next
    INDEX
    Explanations

    programmatic constructs and code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UILabel
    -0.51
     tố
    -0.48
    RequestMapping
    -0.46
     nil
    -0.46
    уда
    -0.46
     Free
    -0.45
     Best
    -0.44
    getMinutes
    -0.44
    ActionButton
    -0.44
    itemize
    -0.43
    POSITIVE LOGITS
    protoimpl
    0.79
     houſe
    0.64
    parsedMessage
    0.63
    istoitu
    0.62
     púb
    0.59
    fjspx
    0.59
     pleaſure
    0.58
     Penh
    0.57
     ujednoznacz
    0.56
    makeConstraints
    0.56
    Activations Density 0.278%

    No Known Activations