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. 23-GEMMASCOPE-RES-16K
    6. 2307
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the remaining or complementary parts of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.59
     PeEnEo
    -0.47
    zzleHttp
    -0.47
     Muhamma
    -0.45
    unternehmen
    -0.45
    AppId
    -0.44
     SqlConnection
    -0.43
    createUser
    -0.43
     Identifier
    -0.42
    channelId
    -0.42
    POSITIVE LOGITS
     rest
    0.92
    rest
    0.89
     Rest
    0.88
    Rest
    0.87
    REST
    0.72
     remainder
    0.70
     resten
    0.69
     REST
    0.68
     übrigen
    0.68
     übri
    0.67
    Activations Density 0.073%

    No Known Activations