© 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. 18-GEMMASCOPE-RES-16K
    11. 8313
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical or scientific notation and references

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

    Symbols within parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    symbols and numbers in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.92
    "},
    -0.85
    /−
    -0.84
    )*/
    -0.81
    ".
    -0.80
    '},
    -0.76
    Personendaten
    -0.76
    ).</
    -0.75
    saraba
    -0.75
    .",
    -0.74
    POSITIVE LOGITS
     punctures
    0.49
    @
    0.47
    ף
    0.46
     Chiron
    0.43
     IIS
    0.43
    O
    0.43
     isola
    0.42
    ->
    0.42
    ợ
    0.41
    ()
    0.41
    Activations Density 0.227%

    No Known Activations