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. 22-GEMMASCOPE-RES-16K
    6. 10234
    Prev
    Next
    INDEX
    Explanations

    references to company operations and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The [the/smaller] followed by a company/club/organization

    np_acts-logits-general · gemini-2.0-flash

    company, organization, club

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Councillor
    -0.48
     polaire
    -0.44
    いろ
    -0.43
    Bands
    -0.42
    jago
    -0.41
    obao
    -0.41
    Clusters
    -0.41
    Eloquent
    -0.41
    érfi
    -0.40
    Cities
    -0.40
    POSITIVE LOGITS
     company
    1.85
     organization
    1.83
     organisation
    1.74
     institution
    1.57
    organization
    1.44
     corporation
    1.38
    company
    1.37
     organisatie
    1.30
     firm
    1.27
    organisation
    1.23
    Activations Density 0.832%

    No Known Activations