Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15922
    Prev
    Next
    INDEX
    Explanations

    topics related to physical interactions and dynamics in quantum systems

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

    instability or equilibrium

    np_acts-logits-general · gemini-2.0-flash

    pitchfork bifurcation phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Busy
    -0.46
     Busy
    -0.44
    busy
    -0.43
     EconPapers
    -0.43
     busy
    -0.42
     Maro
    -0.41
    zkod
    -0.40
    XmlAccessorType
    -0.40
    ctools
    -0.39
     úteis
    -0.39
    POSITIVE LOGITS
     instability
    0.74
     phenomena
    0.74
     phenomenon
    0.68
     unstable
    0.66
     stable
    0.64
     Instability
    0.63
    stable
    0.58
     stability
    0.57
     onset
    0.56
     stabilizing
    0.54
    Activations Density 1.416%

    No Known Activations