© 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. 10708
    Prev
    Next
    INDEX
    Explanations

    technical terminology and references related to research methods and findings

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

    Characters or symbols after certain tokens

    np_acts-logits-general · gemini-2.0-flash

    chess results

    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
     viață
    -0.67
    Життєпис
    -0.64
    WithIOException
    -0.59
    </h1>
    -0.55
     ușor
    -0.52
    </b>
    -0.50
     sari
    -0.50
    קישורים
    -0.49
     pob
    -0.49
     tyto
    -0.49
    POSITIVE LOGITS
     …
    1.13
     فريبيس
    0.84
     […]
    0.83
     …”
    0.80
    rrggbb
    0.76
     ….
    0.73
    […]
    0.72
     …)
    0.72
    ReusableCell
    0.67
     ……
    0.66
    Activations Density 1.089%

    No Known Activations