© 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. 9-GEMMASCOPE-RES-16K
    6. 1709
    Prev
    Next
    INDEX
    Explanations

    structure or formatting elements in code and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.52
    et
    -0.51
    RR
    -0.51
    ⓧ
    -0.45
    f
    -0.45
     of
    -0.45
    &#
    -0.44
    SequentialGroup
    -0.44
    …
    -0.43
     pierna
    -0.42
    POSITIVE LOGITS
    extAlignment
    1.05
    AnchorStyles
    1.00
     الحره
    0.93
    ंदीखरीदारी
    0.89
    ^(@)
    0.88
    NUMX
    0.84
     Majefty
    0.81
     BorderSide
    0.81
    virons
    0.80
     كومونز
    0.79
    Activations Density 0.666%

    No Known Activations