© 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. 27-GEMMASCOPE-RES-16K
    6. 9419
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to specific individuals or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gost
    -0.41
     access
    -0.36
     základní
    -0.35
     zug
    -0.34
     parts
    -0.33
     Branca
    -0.33
    vermögen
    -0.33
    jší
    -0.33
     minimum
    -0.33
     basic
    -0.33
    POSITIVE LOGITS
    󠁣
    0.63
    rungsseite
    0.62
    enterOuterAlt
    0.54
     himſelf
    0.53
    AutoField
    0.52
    UnusedPrivate
    0.51
     viewType
    0.51
    AddTagHelper
    0.50
     Monfieur
    0.50
     setError
    0.49
    Activations Density 0.264%

    No Known Activations