© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 676
    Prev
    Next
    INDEX
    Explanations

    specific terms and identifiers related to programming or technical specifications

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

    numbers and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.51
    })*/
    -0.47
    +#+
    -0.46
    makeText
    -0.45
     BoxFit
    -0.45
    ParseTree
    -0.44
    WaitGroup
    -0.44
    sofá
    -0.43
    ConstraintMaker
    -0.42
    tagHelperRunner
    -0.42
    POSITIVE LOGITS
    Jeografia
    0.49
     Administrativna
    0.42
     autorytatywna
    0.41
    iya
    0.39
    STR
    0.38
    fiez
    0.38
    лтамалар
    0.38
     optimise
    0.38
    upol
    0.38
    Демографія
    0.36
    Activations Density 0.025%

    No Known Activations