Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14470
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to data retrieval and manipulation in programming contexts

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

    Tokens before parentheses or identifiers

    np_acts-logits-general · gemini-2.0-flash

    method calls

    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
     Chwiliwch
    -0.55
    ruct
    -0.53
    ográficos
    -0.52
    pfung
    -0.52
    zeß
    -0.52
     findOne
    -0.52
    setCharacter
    -0.51
    ]]=
    -0.51
     tartalomajánló
    -0.50
     <<=
    -0.50
    POSITIVE LOGITS
    ()->
    0.80
    ().
    0.78
    ContentAsync
    0.69
    ()
    0.65
     ().
    0.64
    (),
    0.63
    ()[
    0.61
    ();
    0.59
    Autoritní
    0.59
    ()}
    0.58
    Activations Density 0.125%

    No Known Activations