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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5421
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.73
    Personendaten
    -0.73
    tagHelperRunner
    -0.71
     يتيمه
    -0.70
    NameInMap
    -0.69
     otomatig
    -0.67
    ThroughAttribute
    -0.65
    styleType
    -0.64
    UrlResolution
    -0.64
    hyrchwyd
    -0.63
    POSITIVE LOGITS
    ]=>
    0.38
    AutoScale
    0.35
     voulons
    0.32
     AppCompatTheme
    0.28
    انيف
    0.27
     océano
    0.26
    mtrl
    0.26
    ISupport
    0.26
    /**
    0.25
    '}>
    0.25
    Activations Density 0.264%

    No Known Activations