© 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. 3261
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "bro" in various contexts

    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
    Lähteet
    -0.55
     gynhyrchwyd
    -0.53
    awtextra
    -0.53
    clearInterval
    -0.47
     []:
    -0.46
     profess
    -0.46
    pageY
    -0.46
     kolei
    -0.45
    infan
    -0.45
    orian
    -0.44
    POSITIVE LOGITS
    casted
    0.63
    featureID
    0.59
    casting
    0.58
    PropertyChanging
    0.57
    StructEnd
    0.55
     betweenstory
    0.54
     <=",
    0.53
     jLabel
    0.52
    luci
    0.50
    CastException
    0.49
    Activations Density 0.200%

    No Known Activations