© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7690
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions, events, or states being described in a narrative context

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

    Past tense verbs suggesting a result or demonstration

    np_acts-logits-general · gemini-2.0-flash

    showed that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.52
     ſche
    -0.52
     houſe
    -0.51
    AsUp
    -0.47
     endblock
    -0.47
     ſy
    -0.43
    ſelf
    -0.42
     now
    -0.42
     agora
    -0.41
     ſtate
    -0.41
    POSITIVE LOGITS
     volna
    0.59
     Chwiliwch
    0.54
    EndInit
    0.51
    bootstrapcdn
    0.51
     took
    0.46
    IContainer
    0.45
    utched
    0.44
     propOrder
    0.44
    Gave
    0.44
    Took
    0.44
    Activations Density 0.987%

    No Known Activations