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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8844
    Prev
    Next
    INDEX
    Explanations

    concepts related to data structures and storage solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Terms related to hashing

    np_acts-logits-general · gemini-2.0-flash

    hashing and hash functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.52
    ArgsConstructor
    -0.48
    yntaxException
    -0.44
    ulipas
    -0.44
    ScopeManager
    -0.44
     transfieras
    -0.44
    RTSC
    -0.43
    netbeans
    -0.43
    begle
    -0.42
    istoitu
    -0.42
    POSITIVE LOGITS
     hashCode
    0.71
    hash
    0.56
     hash
    0.55
    hashCode
    0.52
     Hash
    0.46
    TagMode
    0.46
    Hash
    0.45
    HASH
    0.45
     hashing
    0.42
    HashTable
    0.39
    Activations Density 0.464%

    No Known Activations