© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6275
    Prev
    Next
    INDEX
    Explanations

    terms and operations related to hashing in programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.56
    ControllerAdvice
    -0.56
    enumii
    -0.54
    BrowserModule
    -0.53
    instan
    -0.51
    zzleHttp
    -0.46
    PreferredItem
    -0.45
    addGroup
    -0.45
    forChild
    -0.44
     Reverso
    -0.44
    POSITIVE LOGITS
     hash
    2.56
    hash
    2.36
     Hash
    2.25
    Hash
    2.25
     HASH
    1.95
    HASH
    1.88
     hashing
    1.81
     hashes
    1.76
    hashes
    1.55
     hashed
    1.38
    Activations Density 0.121%

    No Known Activations