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. 8693
    Prev
    Next
    INDEX
    Explanations

    variations of punctuation in the text

    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
    Manbalar
    -0.54
    more
    -0.52
    Παραπομπές
    -0.51
     //$
    -0.49
    EOUS
    -0.49
    𓃵
    -0.48
    tvguidetime
    -0.48
    loài
    -0.48
    ioutil
    -0.47
    matchCondition
    -0.47
    POSITIVE LOGITS
    C
    1.48
    S
    1.46
    E
    1.46
    A
    1.44
    M
    1.43
    P
    1.37
    L
    1.36
    R
    1.36
    D
    1.35
    F
    1.32
    Activations Density 0.347%

    No Known Activations