© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 415
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or sequences in numerical or symbolic formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffible
    -0.89
     Efq
    -0.77
     itſelf
    -0.76
     purpoſe
    -0.76
     occaf
    -0.76
     ſche
    -0.74
     myſelf
    -0.73
     houſe
    -0.73
     himſelf
    -0.73
     iſt
    -0.71
    POSITIVE LOGITS
     $.
    0.73
    $.
    0.69
    ($.
    0.68
    ModelForm
    0.65
    }$.
    0.63
    Portale
    0.61
    ')[
    0.56
    }.
    0.56
    >`;
    0.55
    $:
    0.54
    Activations Density 0.046%

    No Known Activations