© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2565
    Prev
    Next
    INDEX
    Explanations

    selections or choices made in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.49
    stunde
    -0.49
    tanleria
    -0.47
    fileSize
    -0.44
    gesellschaft
    -0.44
     efeitos
    -0.43
     Wayback
    -0.43
    Tikang
    -0.42
     infrastructure
    -0.42
     effects
    -0.42
    POSITIVE LOGITS
     choice
    1.17
     chosen
    1.10
     choose
    1.08
     choosing
    1.07
    choice
    1.06
     Choosing
    1.05
    choosing
    1.04
     선택
    1.04
     Choice
    1.03
    chosen
    1.03
    Activations Density 0.246%

    No Known Activations