© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2624
    Prev
    Next
    INDEX
    Explanations

    concepts related to context-dependent interpretations and varying outcomes

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

    words or phrases that describe variability, inconsistency, or contradictory qualities depending on context or circumstances.

    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
    NameInMap
    -0.44
     defaultstate
    -0.42
    COUVER
    -0.42
    })();
    
    -0.40
    httphttps
    -0.36
     suspected
    -0.35
    huan
    -0.35
    ikala
    -0.35
    ådet
    -0.35
    AttributeName
    -0.34
    POSITIVE LOGITS
     depending
    3.78
    depending
    3.34
     Depending
    3.02
     dependiendo
    2.98
     depends
    2.98
    Depending
    2.95
     Depends
    2.77
    depends
    2.66
     depend
    2.61
    Depends
    2.59
    Activations Density 1.692%

    No Known Activations