Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1026
    Prev
    Next
    INDEX
    Explanations

    assignments and initializations in programming code

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

    coupling parts

    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
     يتيمه
    -0.68
     дописавши
    -0.67
     estekak
    -0.63
    mybatisplus
    -0.63
    новништво
    -0.62
    isContained
    -0.61
    XmlAccessorType
    -0.61
    matchCondition
    -0.60
    TemporalType
    -0.56
    TestBed
    -0.56
    POSITIVE LOGITS
     Finally
    0.45
     infine
    0.42
     finally
    0.40
    Finally
    0.39
     Clean
    0.39
    Sand
    0.38
    }}}}
    0.38
     Sand
    0.38
    ")}
    0.38
    menuStrip
    0.37
    Activations Density 0.046%

    No Known Activations