© 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. 8-GEMMASCOPE-RES-16K
    6. 11514
    Prev
    Next
    INDEX
    Explanations

    information related to company identities and credentials

    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
     الحره
    -0.83
    =$?
    -0.63
    ftagPool
    -0.63
     بيها
    -0.61
     stanovnika
    -0.59
     OnTriggerEnter
    -0.59
    ceptar
    -0.54
     Roskov
    -0.52
    aos
    -0.52
     ROL
    -0.51
    POSITIVE LOGITS
     company
    0.69
     firm
    0.64
     Ltd
    0.64
     Company
    0.62
     empresa
    0.62
    interopRequire
    0.60
     Inc
    0.59
    Company
    0.57
    company
    0.57
     LLC
    0.55
    Activations Density 0.397%

    No Known Activations