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. 4-GEMMASCOPE-RES-16K
    6. 3170
    Prev
    Next
    INDEX
    Explanations

    references to data or experimental results related to quantification or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.78
    WriteBarrier
    -0.76
     Normdatei
    -0.70
    runApp
    -0.60
    +#+
    -0.58
    ReusableCell
    -0.57
    ErrUnexpectedEOF
    -0.57
    aarrggbb
    -0.57
     StringField
    -0.56
     AssemblyCulture
    -0.55
    POSITIVE LOGITS
    ⓘ
    0.58
    CrossRef
    0.54
     Jock
    0.54
    مصادر
    0.53
     مشين
    0.51
    citep
    0.51
    Év
    0.51
     Orrell
    0.50
     FishBase
    0.50
    iastical
    0.49
    Activations Density 1.232%

    No Known Activations