© 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. 9-GEMMASCOPE-RES-16K
    6. 9763
    Prev
    Next
    INDEX
    Explanations

    extended phrases or clauses, particularly at the beginning of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
     soeur
    -0.45
     peixes
    -0.44
    ⓧ
    -0.44
    exels
    -0.42
    wnętr
    -0.39
    ljen
    -0.38
    μφωνα
    -0.38
     ponemos
    -0.37
     haremos
    -0.37
     perchè
    -0.37
    POSITIVE LOGITS
     —
    1.64
    —
    1.21
    .—
    1.16
     —,
    1.13
    ,—
    1.10
    )—
    1.06
    ?—
    1.05
    —.
    1.04
    —"
    1.01
    ———
    1.00
    Activations Density 0.457%

    No Known Activations