© 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. 2-GEMMASCOPE-RES-16K
    6. 13309
    Prev
    Next
    INDEX
    Explanations

    coding terms and diagnostics related to data structures and memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.47
    gnal
    -0.41
    LookAnd
    -0.37
    Tikang
    -0.37
     groet
    -0.36
    hyrchwyd
    -0.36
     disant
    -0.34
     étoit
    -0.34
     realista
    -0.33
     étrangère
    -0.33
    POSITIVE LOGITS
     DT
    1.35
     DS
    1.34
     DP
    1.32
    DT
    1.27
    DP
    1.23
     DH
    1.20
     DC
    1.17
     DF
    1.16
    dz
    1.16
     dt
    1.14
    Activations Density 0.735%

    No Known Activations