© 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. 16-GEMMASCOPE-RES-16K
    11. 8756
    Prev
    Next
    INDEX
    Explanations

    statistics related to goals scored by a player

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

    accumulation or numbering

    np_acts-logits-general · gemini-2.0-flash

    cumulative stats or records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -0.51
     did
    -0.49
    (!__
    -0.48
     ang
    -0.45
    Gemeinden
    -0.45
    getBean
    -0.44
     mesmo
    -0.43
     Was
    -0.43
    Last
    -0.42
    geti
    -0.42
    POSITIVE LOGITS
     cumulative
    0.99
     acumula
    0.99
     accumulated
    0.98
     accum
    0.94
    cumulative
    0.94
     Accum
    0.93
     accumulator
    0.89
     accumulate
    0.87
    findpost
    0.87
    Accum
    0.85
    Activations Density 0.217%

    No Known Activations