© 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. 35-GEMMASCOPE-RES-16K
    11. 7673
    Prev
    Next
    INDEX
    Explanations

    phrases indicating self-reflection and identity within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.59
    出版年
    -0.53
     GenerationType
    -0.48
    RuleContext
    -0.47
    BASELINE
    -0.46
    sonaro
    -0.43
    adpleegd
    -0.43
    AndEndTag
    -0.42
    Brock
    -0.42
     nakalista
    -0.41
    POSITIVE LOGITS
    InThe
    0.85
    inthe
    0.81
     dans
    0.52
     στο
    0.47
     nel
    0.44
     trong
    0.44
    อยู่ใน
    0.43
     في
    0.43
     DANS
    0.42
    ใน
    0.41
    Activations Density 1.305%

    No Known Activations