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

    Neuronpedia

    APICircuit 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. 13-GEMMASCOPE-RES-16K
    6. 11715
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific instruments and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.12
    tagHelperRunner
    -1.08
     mergeFrom
    -1.08
    setVerticalGroup
    -1.00
    SharedCtor
    -0.98
    LookAnd
    -0.98
    UnusedPrivate
    -0.98
    (!__
    -0.93
     CreateTagHelper
    -0.92
    MigrationBuilder
    -0.90
    POSITIVE LOGITS
    </em>
    0.88
    </h5>
    0.71
    </u>
    0.59
    </i>
    0.58
     */
    0.47
    ,
    0.44
    ‘
    0.43
    </s>
    0.43
    éndole
    0.42
    </h6>
    0.41
    Activations Density 0.125%

    No Known Activations