© 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. 14185
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'i' in various contexts

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

    Code snippets with looping variables i, j, k

    np_acts-logits-general · gemini-2.0-flash

    loop variables and assignments

    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
     समीक्षाओं
    -0.69
    ]--;
    -0.69
     ModelExpression
    -0.68
    RTLD
    -0.68
    ieteur
    -0.68
    (!__
    -0.67
     nakalista
    -0.67
    évaluateur
    -0.64
    UnusedPrivate
    -0.62
    XmlAccessType
    -0.61
    POSITIVE LOGITS
     CreateTagHelper
    0.55
     =
    0.53
    apunov
    0.53
    CloseOperation
    0.48
     ExecuteAsync
    0.48
     fallecimiento
    0.47
     Wrote
    0.47
     vestir
    0.47
     tqdm
    0.45
    joje
    0.43
    Activations Density 0.066%

    No Known Activations