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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 13065
    Prev
    Next
    INDEX
    Explanations

    instances of refusal or denial related to requests or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prit
    -0.60
    WebAPI
    -0.59
    icode
    -0.59
     mar
    -0.57
    omoto
    -0.56
     Marta
    -0.55
     dalamnya
    -0.54
     Marat
    -0.54
    +:+
    -0.54
    blogspot
    -0.54
    POSITIVE LOGITS
     Refuse
    1.38
     refusal
    1.35
     refusing
    1.23
     refuser
    1.21
     refuse
    1.19
     refusé
    1.15
     refuses
    1.14
     refused
    1.10
     refus
    1.09
     viewType
    1.09
    Activations Density 0.206%

    No Known Activations