Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5887
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and unresolved issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.51
    SequentialGroup
    -0.48
    Jeografia
    -0.45
     createSprite
    -0.44
    ThroughAttribute
    -0.43
     surla
    -0.42
    AxisAlignment
    -0.41
    richTextPanel
    -0.41
    setVerticalGroup
    -0.39
    oa̍t
    -0.39
    POSITIVE LOGITS
     yet
    4.56
    yet
    3.70
    Yet
    3.58
     Yet
    3.53
     YET
    2.95
     ännu
    2.33
     endnu
    2.28
     jeszcze
    1.98
     еще
    1.81
     Pourtant
    1.80
    Activations Density 0.655%

    No Known Activations