© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5542
    Prev
    Next
    INDEX
    Explanations

    repeated references to entities or concepts associated with "En"

    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
    Politik
    -0.48
     politik
    -0.47
    ">—
    -0.45
    POLIT
    -0.43
     Politik
    -0.41
    politico
    -0.41
    IL
    -0.41
     Politics
    -0.40
    بق
    -0.40
    adple
    -0.38
    POSITIVE LOGITS
    Rule
    0.59
     ModelExpression
    0.58
     تضيفلها
    0.48
     Rule
    0.44
    enderror
    0.44
     Turquía
    0.44
     NSCoder
    0.42
    abinieri
    0.40
    lapsingToolbar
    0.40
     added
    0.40
    Activations Density 0.083%

    No Known Activations