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. 13824
    Prev
    Next
    INDEX
    Explanations

    instances of conditional or alternative phrasing

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

    Number ranges (two, three, four, etc.)

    np_acts-logits-general · gemini-2.0-flash

    numerical ranges or alternatives

    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
    LookAnd
    -0.61
     חיצוניים
    -0.60
    MLLoader
    -0.59
    StoryboardSegue
    -0.58
     medier
    -0.57
    eraard
    -0.56
    VolleyError
    -0.54
     Secretariat
    -0.53
     jLabel
    -0.52
     secretariat
    -0.52
    POSITIVE LOGITS
     Audiodateien
    0.69
     kaarangay
    0.64
    AnimationsModule
    0.57
     sometimes
    0.57
    NameInMap
    0.56
     occasionally
    0.52
     dAtA
    0.47
     maybe
    0.47
     kadang
    0.47
     '\\;'
    0.47
    Activations Density 0.146%

    No Known Activations