© 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. 5395
    Prev
    Next
    INDEX
    Explanations

    assertive phrases indicating certainty or inevitability

    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
    contentLoaded
    -0.60
     hObject
    -0.60
    pecabe
    -0.60
    uxxxx
    -0.58
    fficio
    -0.57
    ⪜
    -0.55
    WriteTagHelper
    -0.54
    cency
    -0.53
    asable
    -0.52
    opia
    -0.52
    POSITIVE LOGITS
     did
    0.74
     does
    0.63
    did
    0.54
     hacerlo
    0.52
    Did
    0.43
     "..\..\
    0.43
    does
    0.41
     melakukannya
    0.41
    LookAnd
    0.40
    そうで
    0.39
    Activations Density 0.230%

    No Known Activations