© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8174
    Prev
    Next
    INDEX
    Explanations

    questions posed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemlig
    -0.48
     kimse
    -0.44
    "}}>
    -0.39
    KindOfClass
    -0.38
     drewna
    -0.38
    spricht
    -0.37
    ⎟
    -0.37
    ViewInit
    -0.36
     kirja
    -0.36
     istri
    -0.35
    POSITIVE LOGITS
    ?)
    2.11
    ?"
    1.97
    ?]
    1.95
    ?’
    1.95
    ?'
    1.93
    ?).
    1.93
    ?”
    1.91
    ?),
    1.90
    ?,
    1.86
    ?;
    1.84
    Activations Density 0.068%

    No Known Activations