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. 9424
    Prev
    Next
    INDEX
    Explanations

    concepts related to relationships and celebrations

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

    symbolic meanings and metaphorical representations of concepts, objects, or themes.

    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
     Roskov
    -0.66
     bParam
    -0.60
     ویکی‌پدی
    -0.49
    usercontent
    -0.44
     millions
    -0.41
     billions
    -0.39
     grotes
    -0.39
    arParams
    -0.39
    CloseOperation
    -0.38
     customised
    -0.38
    POSITIVE LOGITS
     affaires
    0.53
     intelek
    0.52
    aarrggbb
    0.50
     négociations
    0.50
    VIRGO
    0.49
    insegna
    0.49
    ceğine
    0.47
     asuntos
    0.47
     problemer
    0.47
     profesión
    0.46
    Activations Density 0.046%

    No Known Activations