© 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. 9-GEMMASCOPE-RES-16K
    11. 8651
    Prev
    Next
    INDEX
    Explanations

    actions and concepts related to bending and flexibility

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

    descriptions of bending or flexing movements, particularly when applied to rigid structures or body parts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.53
     gynhyrchwyd
    -0.49
     Revel
    -0.47
     rand
    -0.46
    sizeCache
    -0.45
    apiClient
    -0.45
    tagHelper
    -0.45
    ьаж
    -0.44
    Revel
    -0.44
     parad
    -0.43
    POSITIVE LOGITS
     bending
    1.35
     bend
    1.30
     Bending
    1.23
     bent
    1.16
     bends
    1.15
    bend
    1.11
     Bend
    1.08
    Bend
    1.06
    bending
    1.05
     Bent
    1.03
    Activations Density 0.365%

    No Known Activations