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. 5875
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming and technical implementations

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

    Comes after punctuation or connectors

    np_acts-logits-general · gemini-2.0-flash

    components and platforms

    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
    struts
    -0.64
    ="@+
    -0.56
     JFrame
    -0.55
    netbeans
    -0.54
     numberOfRows
    -0.51
     onPostExecute
    -0.51
    SuppressLint
    -0.50
    jfree
    -0.49
     ReactDOM
    -0.49
    ejb
    -0.49
    POSITIVE LOGITS
    ]-'
    0.60
     zod
    0.60
     INTERESAR
    0.59
     تانيه
    0.56
     CANAL
    0.55
     Envoy
    0.55
     MATTER
    0.54
     Embar
    0.52
    ostok
    0.52
    telsen
    0.52
    Activations Density 0.947%

    No Known Activations