© 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. 16-GEMMASCOPE-RES-16K
    6. 1078
    Prev
    Next
    INDEX
    Explanations

    topics related to options, decisions, and the outcomes of processes

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

    preceding verbs/auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    conditions, factors, and decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gira
    -0.52
    tvguidetime
    -0.51
    garet
    -0.46
     Pari
    -0.45
    restre
    -0.44
    weber
    -0.43
    ETR
    -0.43
     raff
    -0.43
     twofold
    -0.43
    aged
    -0.42
    POSITIVE LOGITS
    AndEndTag
    1.11
     ModelExpression
    0.81
     exists
    0.76
     ensued
    0.75
     الحره
    0.75
     emerged
    0.71
    MessageOf
    0.69
    HasForeignKey
    0.68
     occurred
    0.68
     kaynağından
    0.68
    Activations Density 0.567%

    No Known Activations