© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and data display

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

    Code, parameters, or indexes

    np_acts-logits-general · gemini-2.0-flash

    parameters and identifiers

    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
    cidae
    -0.55
    NOPQRST
    -0.53
     Normdatei
    -0.48
     विश्वसनीयता
    -0.47
    szönöm
    -0.46
     uVar
    -0.44
    řeba
    -0.43
    ArgsConstructor
    -0.43
    참고
    -0.43
    sinon
    -0.43
    POSITIVE LOGITS
    Geplaatst
    0.63
     články
    0.57
    Identyfik
    0.56
    %")
    0.56
    alsy
    0.56
    $")
    0.54
    Explicación
    0.53
     Protobuf
    0.53
     key
    0.53
     iconFacebook
    0.53
    Activations Density 0.063%

    No Known Activations