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. 20-GEMMASCOPE-RES-16K
    6. 3330
    Prev
    Next
    INDEX
    Explanations

    aspects related to database configurations and parameters

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

    Tokens followed by JSON-like values

    np_acts-logits-general · gemini-2.0-flash

    maximum value and database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.77
    StructField
    -0.74
    StructEnd
    -0.73
    AddTagHelper
    -0.73
    NSNotification
    -0.72
    omány
    -0.69
    bbene
    -0.69
    writeField
    -0.67
     Roskov
    -0.67
    czaj
    -0.66
    POSITIVE LOGITS
    ally
    0.98
    cination
    0.84
    ALLY
    0.79
    Advertisements
    0.77
    ANGER
    0.71
    EUROPA
    0.68
    ので
    0.66
    OKAY
    0.65
    feren
    0.63
    ization
    0.63
    Activations Density 1.016%

    No Known Activations