© 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. 11-GEMMASCOPE-RES-16K
    6. 6430
    Prev
    Next
    INDEX
    Explanations

    structured data elements and properties in JSON or similar formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.71
    ImageContext
    -0.67
    InitVars
    -0.63
    bewerken
    -0.60
    LookAnd
    -0.60
     utafitiHapana
    -0.58
     FetchType
    -0.55
    فایل‌لار
    -0.55
    AllAfrica
    -0.55
    Hozzáférés
    -0.53
    POSITIVE LOGITS
    <td>
    0.57
    none
    0.56
    Hentet
    0.54
    "]="
    0.53
    )}{(
    0.53
    meris
    0.53
     none
    0.52
    》:
    0.51
    ocarcinoma
    0.51
    }=(
    0.51
    Activations Density 0.534%

    No Known Activations