© 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. 7707
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court proceedings and legal decisions

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

    Assertions, arguments, or statements

    np_acts-logits-general · gemini-2.0-flash

    saying or claiming something

    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
    Personensuche
    -0.44
    SetBool
    -0.43
    DockStyle
    -0.42
    uitton
    -0.40
     thôi
    -0.39
    GTCX
    -0.39
    ลำ
    -0.38
    それにしても
    -0.36
     yes
    -0.35
    ignes
    -0.35
    POSITIVE LOGITS
     saying
    1.23
     citing
    1.20
    saying
    1.18
     claiming
    1.12
     arguing
    1.11
     believing
    1.04
     alleging
    1.00
    Saying
    0.99
     stating
    0.98
     Saying
    0.96
    Activations Density 0.752%

    No Known Activations