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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 36021
    Prev
    Next
    INDEX
    Explanations

    code-related terms and example references in programming context

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

    example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymal
    -0.48
    SourceChecksum
    -0.47
    sober
    -0.46
    ichu
    -0.46
    Brainz
    -0.45
    pae
    -0.44
     utf
    -0.41
    peto
    -0.41
    dut
    -0.40
     ern
    -0.40
    POSITIVE LOGITS
    Example
    1.58
    ByExample
    1.47
     Example
    1.36
     example
    1.27
    example
    1.23
     EXAMPLE
    1.16
     Beispiel
    1.13
    Examples
    1.12
    Exemple
    1.12
    Beispiel
    1.08
    Activations Density 0.001%

    No Known Activations