© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10001
    Prev
    Next
    INDEX
    Explanations

    strings that represent structured data in a programming-like syntax

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

    Code block delimiters and related syntax

    np_acts-logits-general · gemini-2.0-flash

    data type and description fields

    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
     name
    -1.76
     Name
    -1.59
    name
    -1.58
    Name
    -1.54
     names
    -1.50
     named
    -1.49
     Namen
    -1.35
     Named
    -1.31
     NAME
    -1.31
    NAME
    -1.30
    POSITIVE LOGITS
    }));
    0.65
    ")));
    0.60
     handleMessage
    0.60
     GenerationType
    0.60
    }))
    0.59
     propOrder
    0.57
     препратки
    0.57
    áda
    0.55
    )";
    0.55
    leece
    0.54
    Activations Density 0.150%

    No Known Activations