© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3611
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in the context of structured data, such as JSON or code

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

    JSON and code structure syntax elements like braces, brackets, and commas that delimit data objects and arrays.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     todella
    -0.36
    期刊论文
    -0.32
    .
    -0.32
     asla
    -0.31
     Stimm
    -0.31
     utama
    -0.31
    wohl
    -0.31
    ュ
    -0.30
    ?
    -0.30
     menim
    -0.30
    POSITIVE LOGITS
    })*/
    0.77
     disambiguazione
    0.73
     },
    0.71
     Roskov
    0.68
     }),
    0.65
    '}),
    0.65
     }))
    0.64
    '],
    0.64
     jspb
    0.64
    -),
    0.62
    Activations Density 0.318%

    No Known Activations