© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 487
    Prev
    Next
    INDEX
    Explanations

    conditional statements involving potential consequences or considerations

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

    conditional clauses beginning with "if" followed by second-person pronouns or verbs.

    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
    الإنجليزية
    -0.38
     zwar
    -0.36
     möglichst
    -0.35
    
    -0.34
     Verfügung
    -0.33
    älv
    -0.33
     Entscheidung
    -0.31
     dormitórios
    -0.31
    stdc
    -0.31
    hésite
    -0.31
    POSITIVE LOGITS
     look
    1.09
     looked
    0.94
    look
    0.90
    Look
    0.89
     Look
    0.89
     compare
    0.86
     consider
    0.84
     LOOK
    0.81
     comparing
    0.81
     examine
    0.80
    Activations Density 0.511%

    No Known Activations