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. 14949
    Prev
    Next
    INDEX
    Explanations

    key terms and identifiers related to scientific publications and their formatting

    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
    argout
    -0.44
     laço
    -0.43
     alluminio
    -0.42
    Халык
    -0.42
     miglia
    -0.41
    getInt
    -0.41
     qualunque
    -0.41
    𝕜
    -0.40
    BackColor
    -0.38
     खिला
    -0.38
    POSITIVE LOGITS
    SBATCH
    0.85
     pleaſure
    0.71
    SequentialGroup
    0.71
    SceneManagement
    0.69
    providedIn
    0.68
     ſy
    0.66
     gynhyrchwyd
    0.65
    SBS
    0.65
     itſelf
    0.65
    sibirsk
    0.64
    Activations Density 4.427%

    No Known Activations