© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2071
    Prev
    Next
    INDEX
    Explanations

    references to time and change in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "the" followed by "end"

    np_acts-logits-general · gemini-2.0-flash

    end of sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.61
     विश्वसनीयता
    -0.55
     defaultstate
    -0.54
    tagHelperRunner
    -0.54
    хьтан
    -0.53
    évaluateur
    -0.53
     CURIAM
    -0.51
     ModelExpression
    -0.50
     pinulongan
    -0.49
    \{\\
    -0.48
    POSITIVE LOGITS
     end
    3.62
    end
    2.69
     End
    2.67
    End
    2.55
     END
    2.38
     ends
    2.16
    END
    1.99
     ended
    1.93
     Ende
    1.91
     ending
    1.90
    Activations Density 0.457%

    No Known Activations