© 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. 2-GEMMASCOPE-RES-16K
    11. 12807
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and their associated context in the text

    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
     noël
    -0.43
     Bupati
    -0.37
    RTEE
    -0.36
    Domestic
    -0.35
     McN
    -0.35
     #
    -0.34
     sucedido
    -0.34
    ไตล์
    -0.33
     célèbre
    -0.33
    Omni
    -0.33
    POSITIVE LOGITS
    $)$
    0.65
    $.}
    0.65
    BufferException
    0.62
    SourceChecksum
    0.58
     {,
    0.55
    MessageOf
    0.54
    󠁮
    0.54
    DockStyle
    0.53
     }}$.
    0.53
     utafitiHapana
    0.52
    Activations Density 0.193%

    No Known Activations