© 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. 3061
    Prev
    Next
    INDEX
    Explanations

    instances of sentence beginnings or structural elements in text

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

    Code snippets or source code

    np_acts-logits-general · gemini-2.0-flash

    genes, soil, income, unleash

    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
     […]
    -0.98
     therefrom
    -0.95
    </h3>
    -0.87
     …
    -0.86
    }$.\\
    -0.84
    <eos>
    -0.82
     thereof
    -0.81
     deren
    -0.77
     them
    -0.77
    ↵
    -0.76
    POSITIVE LOGITS
    ^(@)
    0.75
    MERCIAL
    0.70
    Gön
    0.68
    帖最后由
    0.67
    AxisAlignment
    0.64
    iſh
    0.64
    CloseOperation
    0.64
    ADRID
    0.62
    ſhip
    0.61
    wiſe
    0.60
    Activations Density 1.094%

    No Known Activations