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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4839
    Prev
    Next
    INDEX
    Explanations

    structured data elements or keys typically seen in JSON or code-related contexts

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

    Values associated with keys in JSON-like structures

    np_acts-logits-general · gemini-2.0-flash

    structured data and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    -0.86
    -0.67
    \
    -0.60
    ;

    -0.58
    (
    -0.53
    *
    -0.53
    ;?>
    -0.51
    /
    -0.51
    )
    -0.49
    ;\
    -0.46
    POSITIVE LOGITS
     "",
    1.10
     '',
    1.05
     [],
    1.02
     {},
    1.01
     "",

    0.84
    null
    0.83
     ”,
    0.82
    "",
    0.82
    '',
    0.82
     null
    0.81
    Activations Density 0.266%
    No Known Activations