© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93351
    Prev
    Next
    INDEX
    Explanations

    themes related to openness and vulnerability in communication and expression

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

    open and honest conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCreateView
    -0.47
    occuper
    -0.45
    muñeca
    -0.44
    blusa
    -0.43
    zeitige
    -0.43
     pewno
    -0.42
    paravant
    -0.42
    phazard
    -0.40
    clusão
    -0.40
    ioc
    -0.39
    POSITIVE LOGITS
     confidential
    0.52
     relax
    0.46
    EDEFAULT
    0.44
    DMETHOD
    0.42
    Relax
    0.42
     Relax
    0.42
    ActionCreators
    0.41
     HttpNotFound
    0.41
     vertra
    0.41
     confid
    0.40
    Activations Density 0.072%

    No Known Activations