© 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. 3-GEMMASCOPE-RES-16K
    6. 8974
    Prev
    Next
    INDEX
    Explanations

    assertions of correctness or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    velocityY
    -0.40
    nodeType
    -0.40
    NameInMap
    -0.39
    Jereo
    -0.39
    ();)
    -0.39
    astéro
    -0.38
    boxShadow
    -0.38
     haka
    -0.38
    opcao
    -0.37
    ölker
    -0.36
    POSITIVE LOGITS
     right
    3.03
     RIGHT
    2.22
     Right
    2.20
    Right
    2.09
    RIGHT
    1.61
    right
    1.52
     rechten
    1.38
     righ
    1.36
    右
    1.35
     derecho
    1.30
    Activations Density 0.085%

    No Known Activations