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. 25-GEMMASCOPE-RES-16K
    6. 7060
    Prev
    Next
    INDEX
    Explanations

    terms related to undulation or variation in structure and properties

    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
    er
    -3.02
    ER
    -1.63
    erate
    -1.44
    erà
    -1.29
    erii
    -1.15
    erl
    -1.15
    erent
    -1.12
    ه
    -1.08
    erai
    -1.07
    erti
    -1.07
    POSITIVE LOGITS
    ERS
    0.64
    erview
    0.61
    erv
    0.57
    erex
    0.57
    ership
    0.56
    erval
    0.54
     paramInt
    0.53
    erson
    0.52
    DoubleQuotes
    0.52
    __":
    
    0.51
    Activations Density 0.674%

    No Known Activations