© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or parts of a whole

    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
     […]
    -0.51
     väli
    -0.49
     ogóle
    -0.49
    IBar
    -0.47
     [...]
    -0.46
     ACTUALLY
    -0.46
     kiin
    -0.45
    AnchorStyles
    -0.44
     interestingly
    -0.44
    adays
    -0.44
    POSITIVE LOGITS
     her
    1.30
     his
    1.16
     your
    1.07
     my
    1.02
     our
    0.95
     him
    0.88
     henne
    0.83
     their
    0.83
     you
    0.80
     me
    0.76
    Activations Density 1.815%

    No Known Activations