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. 7996
    Prev
    Next
    INDEX
    Explanations

    default values and settings related to configurations

    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
     jSON
    -0.62
     XMLHttpRequest
    -0.57
     telefónica
    -0.56
    XmlAccessorType
    -0.53
     fileSize
    -0.53
     JSONException
    -0.53
     phoneNumber
    -0.52
    encodeWith
    -0.51
     psycopg
    -0.51
    getJSONObject
    -0.50
    POSITIVE LOGITS
    Default
    1.30
    default
    1.27
     Default
    1.26
     default
    1.26
    setDefault
    1.13
    DEFAULT
    1.13
     DEFAULT
    1.05
    getDefault
    0.97
     defaulted
    0.95
    defaults
    0.92
    Activations Density 0.084%

    No Known Activations