© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10360
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpretation and contextual analysis of meaning

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

    language related to interpretation and understanding of meaning.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.38
    __':
    -0.38
    Bakgrunnsstoff
    -0.33
    <caption>
    -0.33
     生命周期
    -0.31
     beker
    -0.31
    様子
    -0.30
    SequentialGroup
    -0.30
     nennt
    -0.30
    Brainz
    -0.30
    POSITIVE LOGITS
     interpretation
    3.19
     interpretations
    2.89
     interpret
    2.88
     Interpretation
    2.86
     interpreting
    2.83
     INTERPRET
    2.75
    interpretation
    2.72
     interpreted
    2.72
    Interpretation
    2.69
     interprets
    2.64
    Activations Density 0.930%

    No Known Activations