© 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. 37-GEMMASCOPE-RES-16K
    6. 3895
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and syntax used for formatting and including figures in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    readFileSync
    -0.33
    скус
    -0.33
    chle
    -0.32
    +#+#
    -0.32
     links
    -0.31
     negro
    -0.31
     peuple
    -0.31
     nectar
    -0.31
    gdx
    -0.30
     sus
    -0.30
    POSITIVE LOGITS
     ویکی‌پدی
    0.67
    RenderAtEndOf
    0.64
    WriteTagHelper
    0.58
     nonUne
    0.57
     الحره
    0.56
    XmlEnum
    0.54
    Personendaten
    0.53
    thenReturn
    0.53
    tanleria
    0.52
     Meksiku
    0.51
    Activations Density 0.246%

    No Known Activations