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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 2143
    Prev
    Next
    INDEX
    Explanations

    references to local entities and communities

    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
    Gambas
    -0.56
    ktop
    -0.56
    UnsafeEnabled
    -0.55
     مرئيه
    -0.52
    ględ
    -0.51
     noDo
    -0.51
    mpada
    -0.50
    ("}\
    -0.49
    anstalt
    -0.49
    findpost
    -0.48
    POSITIVE LOGITS
     local
    1.19
     locals
    1.15
     lokale
    1.15
     locally
    1.14
     Locals
    1.12
    locally
    1.10
    Local
    1.10
    local
    1.10
     Locally
    1.07
     LOCAL
    1.04
    Activations Density 0.136%

    No Known Activations