© 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. 20-GEMMASCOPE-RES-16K
    6. 3945
    Prev
    Next
    INDEX
    Explanations

    words related to desires and requests for specific outcomes or properties

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

    phrases expressing desire or intention, particularly using words like "want", "need", and "desired".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })).
    -0.30
    </b>
    -0.29
    ])[
    -0.28
    <bos>
    -0.28
     common
    -0.27
    </strong>
    -0.26
     raw
    -0.26
     rich
    -0.24
     collective
    -0.24
     Gi
    -0.23
    POSITIVE LOGITS
    SourceChecksum
    0.79
    majánló
    0.76
    PreferredItem
    0.75
     zwiſchen
    0.74
     laſſen
    0.73
    exitRule
    0.73
     Bewußt
    0.73
    iſche
    0.72
    <pad>
    0.72
    <unused28>
    0.72
    Activations Density 0.314%

    No Known Activations