© 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. 4-GEMMASCOPE-RES-16K
    6. 12669
    Prev
    Next
    INDEX
    Explanations

    references and attributions to the source of information

    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
    ghijklmnop
    -0.80
    InputBorder
    -0.79
    ImageContext
    -0.75
    ThroughAttribute
    -0.74
     ostavi
    -0.74
    berdayakan
    -0.72
    ipment
    -0.72
    intenance
    -0.72
     насељу
    -0.72
     Efq
    -0.71
    POSITIVE LOGITS
     according
    1.34
    according
    1.24
    According
    1.22
    Según
    1.22
     According
    1.20
     selon
    1.19
     según
    1.18
     Según
    1.13
     Selon
    1.12
     לפי
    1.12
    Activations Density 0.442%

    No Known Activations