© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1222
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and data related to research and analysis in biotechnology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.17
    +#+#
    -1.12
    AnchorStyles
    -1.11
    PyExc
    -1.08
     محفوظة
    -1.06
    UserScript
    -1.04
    Portale
    -1.03
    AutoScaleMode
    -1.03
    windowFixed
    -1.01
     Wicidata
    -1.01
    POSITIVE LOGITS
    <b>
    0.53
    <strong>
    0.50
    ;
    0.46
     tovább
    0.45
    </h5>
    0.41
     επίσης
    0.41
    .
    0.40
    ↵
    0.40
    N
    0.39
     pertama
    0.38
    Activations Density 1.070%

    No Known Activations