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. 25-GEMMASCOPE-RES-16K
    6. 4185
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms associated with monetary values and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CH
    -1.44
    ch
    -1.42
    CH
    -1.40
     ch
    -1.36
    Ch
    -1.34
     Ch
    -1.34
    chi
    -1.21
     Chi
    -1.20
    ACH
    -1.20
    chis
    -1.20
    POSITIVE LOGITS
     Cullen
    0.60
    pielt
    0.59
    pielen
    0.57
    pannt
    0.57
    timmt
    0.49
    ArgsConstructor
    0.47
     CUB
    0.45
     Cowan
    0.45
     HAV
    0.45
     cuba
    0.45
    Activations Density 3.818%

    No Known Activations