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. 6275
    Prev
    Next
    INDEX
    Explanations

    terms related to components and mechanisms used for mounting

    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
     Sarg
    -0.89
    addGap
    -0.84
    djangoproject
    -0.71
    Ucraina
    -0.68
     GenerationType
    -0.67
     MediatR
    -0.67
    InjectAttribute
    -0.66
     timedelta
    -0.65
    fastjson
    -0.65
    Hochspringen
    -0.64
    POSITIVE LOGITS
     mounts
    1.73
     Mounts
    1.73
     mount
    1.68
     MOUNT
    1.67
     Mount
    1.62
    Mount
    1.57
     mounted
    1.56
    MOUNT
    1.55
    mounted
    1.48
    mount
    1.46
    Activations Density 0.103%

    No Known Activations