© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3679
    Prev
    Next
    INDEX
    Explanations

    connections between familial identities and their attributes within complex systems

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

    words that convey becoming or transformation, particularly in contexts describing change, possibility, or transition.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.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
    Географиясе
    -0.33
     ब्रेकडाउन
    -0.32
    ksessa
    -0.31
    ientemente
    -0.31
    があり
    -0.31
    нительно
    -0.31
     faltan
    -0.31
     недавно
    -0.31
    dotenv
    -0.30
    違います
    -0.30
    POSITIVE LOGITS
     become
    2.48
     becomes
    2.45
     became
    2.16
     becoming
    2.13
    become
    2.09
    becomes
    2.05
     Become
    2.03
     Becomes
    2.02
    Become
    1.91
    became
    1.84
    Activations Density 1.298%

    No Known Activations