© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    references to auditory experiences, particularly screams and noises associated with distress

    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
    ifrance
    -0.58
    AddField
    -0.52
    ueba
    -0.49
     utafitiHapana
    -0.49
    XmlType
    -0.49
     Tapatalk
    -0.48
     solare
    -0.48
     teil
    -0.47
     ivelany
    -0.47
    AndEndTag
    -0.47
    POSITIVE LOGITS
     clicking
    0.89
     sounds
    0.86
     noises
    0.86
     voices
    0.84
     rustling
    0.83
     clicks
    0.83
     laughter
    0.83
     cries
    0.82
     crackling
    0.81
     footsteps
    0.81
    Activations Density 0.322%

    No Known Activations