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. 11-GEMMASCOPE-RES-16K
    6. 7470
    Prev
    Next
    INDEX
    Explanations

    words associated with the film industry and cinematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.90
    +/**
    -0.89
    Enlaces
    -0.86
    ++++++++++++++++
    -0.84
    >"+
    -0.77
     برانيه
    -0.76
    >'+
    -0.76
    endphp
    -0.74
    ••••
    -0.73
    LocalTime
    -0.71
    POSITIVE LOGITS
     Sk
    1.11
     Scully
    1.08
     SCA
    1.08
     Sc
    1.07
    Sk
    1.05
     SC
    1.04
    Sc
    1.02
     sc
    1.00
     Sko
    0.99
     SCO
    0.98
    Activations Density 0.147%

    No Known Activations