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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 11729
    Prev
    Next
    INDEX
    Explanations

    headings or section indicators within a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.56
    <h1>
    -0.54
    <bos>
    -0.54
     conse
    -0.49
    </tbody>
    -0.49
     body
    -0.49
     Steen
    -0.46
    "]
    -0.45
    exitRule
    -0.44
     }{\
    -0.44
    POSITIVE LOGITS
     intptr
    0.84
    tagHelperRunner
    0.81
    mybatisplus
    0.77
    +#+
    0.74
    rizona
    0.73
     AssemblyCulture
    0.72
    adə
    0.71
     Wiktionnaire
    0.71
     disambiguazione
    0.70
    íncia
    0.69
    Activations Density 0.026%

    No Known Activations