© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2947
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions, their effects, or changes in states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    explicit references to processes and outcomes related to quality assessment and evaluation

    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
     and
    -3.13
     và
    -1.53
    และ
    -1.47
    and
    -1.46
     и
    -1.46
    性和
    -1.40
     \&
    -1.34
     &
    -1.33
     AND
    -1.32
    子和
    -1.28
    POSITIVE LOGITS
     Alternatively
    0.57
     poveznice
    0.55
     aught
    0.53
    Alternatively
    0.53
     thereof
    0.50
     alguno
    0.45
    Oder
    0.45
    )_/¯
    0.45
     oder
    0.45
     accordingly
    0.43
    Activations Density 2.436%

    No Known Activations