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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 12733
    Prev
    Next
    INDEX
    Explanations

    structured data formats like JSON or tabular representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.92
    varargin
    -0.80
     مرئيه
    -0.76
    NUMX
    -0.75
     الحره
    -0.74
    RegressionTest
    -0.74
    UserScript
    -0.73
    didSet
    -0.72
    SPATH
    -0.71
     ويكيميديا
    -0.71
    POSITIVE LOGITS
     
    0.75
    1
    0.51
    q
    0.43
     {
    0.42
    s
    0.42
    un
    0.41
    6
    0.41
    h
    0.41
    7
    0.40
     Metropolitana
    0.40
    Activations Density 1.258%

    No Known Activations