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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1525
    Prev
    Next
    INDEX
    Explanations

    legal and administrative processes related to charges and decisions from authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mourut
    -0.53
     enfans
    -0.51
     sanitaires
    -0.48
     graciosas
    -0.46
    nyata
    -0.46
     spectateurs
    -0.45
    Ten
    -0.44
     mètre
    -0.43
     étrangers
    -0.43
    bbene
    -0.42
    POSITIVE LOGITS
    principalTable
    0.98
    ValueStyle
    0.91
    IsContent
    0.81
     صوتيه
    0.76
    Geplaatst
    0.73
    zzleHttp
    0.71
    AndEndTag
    0.71
    SourceChecksum
    0.71
     الحره
    0.69
     Wicidata
    0.69
    Activations Density 0.265%

    No Known Activations