© 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. 10-GEMMASCOPE-RES-16K
    6. 2030
    Prev
    Next
    INDEX
    Explanations

    specific legal and procedural terms related to certifications and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.48
     Quij
    -0.44
    $\%
    -0.44
    કો
    -0.44
    SetFont
    -0.44
     Cor
    -0.44
     review
    -0.43
    Linq
    -0.43
     Sign
    -0.42
    enguin
    -0.42
    POSITIVE LOGITS
     transfieras
    0.86
    ########.
    0.81
    OGND
    0.69
    VersionUID
    0.64
     distanciation
    0.63
    VIAF
    0.62
    DrawerToggle
    0.60
    balleur
    0.60
    AndEndTag
    0.59
    UIControlState
    0.56
    Activations Density 0.713%

    No Known Activations