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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 14549
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to research methodologies and participant selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.71
     CreateTagHelper
    -0.68
    RectangleBorder
    -0.64
     actionTypes
    -0.61
    ImageContext
    -0.60
    例文帳に追加
    -0.57
    UnknownFieldSet
    -0.56
    verwijspagina
    -0.55
    //
    -0.55
    SceneManagement
    -0.54
    POSITIVE LOGITS
     outreach
    0.57
     prospecting
    0.56
    everywhere
    0.55
     Everywhere
    0.53
     solicitation
    0.53
    قایناق‌لار
    0.53
     canv
    0.53
     soliciting
    0.53
    numerusform
    0.52
     everywhere
    0.52
    Activations Density 0.364%

    No Known Activations