© 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. 0-GEMMASCOPE-RES-16K
    11. 2414
    Prev
    Next
    INDEX
    Explanations

    reflections on self-identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fehlung
    -0.45
     CanadaChoose
    -0.44
     padx
    -0.42
    rachtet
    -0.42
    Atsauces
    -0.41
    wsdl
    -0.36
    Gdx
    -0.36
    pageY
    -0.36
     Cry
    -0.34
    ITAL
    -0.34
    POSITIVE LOGITS
     themselves
    3.94
     herself
    3.91
     himself
    3.88
     yourself
    3.83
     ourselves
    3.72
     itself
    3.56
    himself
    3.53
    themselves
    3.50
     oneself
    3.48
     Himself
    3.42
    Activations Density 0.128%

    No Known Activations