© 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. 22-GEMMASCOPE-RES-16K
    6. 11349
    Prev
    Next
    INDEX
    Explanations

    references to various industries and technologies

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

    "In" followed by a specific topic or field

    np_acts-logits-general · gemini-2.0-flash

    in particular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.67
     EconPapers
    -0.64
     незавершена
    -0.63
     hObject
    -0.63
     getItemId
    -0.62
     viewType
    -0.60
     lenker
    -0.60
    KURZBESCHREIBUNG
    -0.59
    Зноскі
    -0.59
     ligiloj
    -0.58
    POSITIVE LOGITS
     especially
    3.98
     particularly
    3.97
     Particularly
    3.64
    particularly
    3.64
    Especially
    3.63
    especially
    3.59
     Especially
    3.52
     especialmente
    3.31
     particularmente
    3.13
     particuli
    2.89
    Activations Density 0.797%

    No Known Activations