© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    conditions or feelings associated with reluctance and hesitation

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

    negative or adversarial statements where someone is unable or unwilling to do something.

    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
    Parcelize
    -0.40
    ]))
    
    -0.38
    "))
    
    -0.36
     diretta
    -0.36
    complexType
    -0.35
     Massen
    -0.35
     eenvoudig
    -0.35
    mappedBy
    -0.35
     juſt
    -0.34
     Reſ
    -0.34
    POSITIVE LOGITS
     budge
    0.68
     überhaupt
    0.65
     invokingState
    0.64
    ंदीखरीदारी
    0.61
     even
    0.59
     vůbec
    0.58
     bothering
    0.55
     existent
    0.55
     bothered
    0.54
    functioning
    0.53
    Activations Density 0.422%

    No Known Activations