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. 9-GEMMASCOPE-RES-16K
    6. 9276
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biçim
    -0.44
     本
    -0.42
     apapun
    -0.42
    ϊ
    -0.42
     heren
    -0.41
    }.
    -0.40
    schuh
    -0.39
    Amount
    -0.39
     ac
    -0.38
    فعل
    -0.38
    POSITIVE LOGITS
     оригіналу
    0.90
    antMatchers
    0.88
    AddHtmlAttribute
    0.88
     useAppContext
    0.85
    Hochspringen
    0.84
     كومونز
    0.81
    postsleuth
    0.77
    providedIn
    0.77
    PreExecute
    0.77
     חיצוניים
    0.76
    Activations Density 0.034%

    No Known Activations