© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8288
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "mis" indicating incorrectness or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.63
     صوتيه
    -0.54
     Cæsar
    -0.53
    InitVars
    -0.53
    marginHorizontal
    -0.51
    
    -0.51
    età
    -0.51
    ClientSize
    -0.50
    ⓘ
    -0.49
     ferma
    -0.46
    POSITIVE LOGITS
    matched
    0.58
    representation
    0.57
    interpretation
    0.56
    haps
    0.55
    givings
    0.55
    évaluateur
    0.54
    ogyn
    0.53
    fits
    0.53
    firing
    0.53
    fires
    0.53
    Activations Density 0.271%

    No Known Activations