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. 8-GEMMASCOPE-RES-16K
    6. 14968
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "multi" and related concepts, indicating a focus on multiplicity or multi-faceted aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppCompatTheme
    -0.84
     resourceCulture
    -0.82
     referrerpolicy
    -0.80
     végétale
    -0.79
     japonais
    -0.78
    ✨:
    -0.77
    })`
    -0.77
     veneta
    -0.76
     grecque
    -0.74
     Grecs
    -0.73
    POSITIVE LOGITS
     Multi
    1.69
     multi
    1.69
    multi
    1.59
    Multi
    1.55
     MULTI
    1.33
    MULT
    1.33
    MULTI
    1.29
     MULT
    1.28
     multilayer
    1.11
     mul
    1.02
    Activations Density 0.140%

    No Known Activations