© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15871
    Prev
    Next
    INDEX
    Explanations

    narratives related to animals and their interactions with humans

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

    phrases describing sudden entry or arrival into a space or situation.

    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
     pergi
    -0.41
     myself
    -0.39
     yourself
    -0.38
    .*")]
    -0.37
     going
    -0.36
     went
    -0.35
    Went
    -0.35
     goes
    -0.35
    回去
    -0.34
     jScrollPane
    -0.34
    POSITIVE LOGITS
    Personendaten
    0.75
     unexpectedly
    0.74
    ReusableCell
    0.66
    suddenly
    0.64
     suddenly
    0.61
    Suddenly
    0.60
     bezeichneter
    0.58
    VolleyError
    0.57
     unexpected
    0.56
     Suddenly
    0.55
    Activations Density 0.353%

    No Known Activations