Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9120
    Prev
    Next
    INDEX
    Explanations

    negations and comparative phrases that express varying degrees of discontent or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparative phrases using "not...nearly as...much/the" to express degree or extent of difference.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    feinander
    -0.48
    sweise
    -0.46
    dchen
    -0.45
     الحره
    -0.45
    ormais
    -0.45
    zzleHttp
    -0.42
     texinfo
    -0.42
     nedenle
    -0.40
    ebvre
    -0.39
    FormBorderStyle
    -0.38
    POSITIVE LOGITS
     autant
    1.25
     altrett
    0.94
     lika
    0.89
     tão
    0.88
     zoveel
    0.82
     genauso
    0.77
     столько
    0.75
     tanta
    0.75
    เท่า
    0.74
     tantas
    0.73
    Activations Density 0.417%

    No Known Activations