© 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. 24-GEMMASCOPE-RES-16K
    11. 5762
    Prev
    Next
    INDEX
    Explanations

    elements related to coding, programming, and technical structures or errors, particularly focusing on variables, strings, and system commands

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

    Followed by non-English suffixes

    np_acts-logits-general · gemini-2.0-flash

    she/her/herself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himself
    -0.72
    Completo
    -0.56
     său
    -0.54
     Jr
    -0.52
     koji
    -0.52
     Himself
    -0.50
     fallu
    -0.49
    himself
    -0.47
    +#+
    -0.47
    存于互联网档案馆
    -0.47
    POSITIVE LOGITS
     herself
    1.12
    herself
    0.98
     her
    0.94
     그녀
    0.92
    彼女の
    0.83
     její
    0.81
    彼女は
    0.79
     she
    0.79
    她
    0.78
     która
    0.77
    Activations Density 0.773%

    No Known Activations