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-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11526
    Prev
    Next
    INDEX
    Explanations

    instances of whitespace or empty characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECONDS
    -0.60
    GTCX
    -0.57
     travailleurs
    -0.52
    xcf
    -0.51
     Shuk
    -0.48
    EFIAPI
    -0.47
    exitRule
    -0.47
    stateMutability
    -0.45
     WORKERS
    -0.44
    RTCF
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.37
    nasium
    0.37
     rocked
    0.33
     Administrativna
    0.33
    -------------</
    0.32
     mema
    0.32
     ako
    0.31
     Volume
    0.30
     resourceCulture
    0.30
    jspb
    0.30
    Activations Density 0.069%

    No Known Activations