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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9112
    Prev
    Next
    INDEX
    Explanations

    references to inventions and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.39
    u
    -0.37
    ↵
    -0.37
     
    -0.35
    l
    -0.35
    s
    -0.33
     Te
    -0.33
    .
    -0.32
    v
    -0.31
    S
    -0.30
    POSITIVE LOGITS
     queſta
    1.06
    <unused51>
    1.05
     kasarigan
    1.05
    <unused23>
    1.05
    <unused43>
    1.05
    <unused8>
    1.04
    <unused16>
    1.04
    <unused3>
    1.04
    <pad>
    1.04
    [@BOS@]
    1.04
    Activations Density 0.388%

    No Known Activations