© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2701
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ricev
    -0.60
    ęg
    -0.59
    thru
    -0.57
    Quoting
    -0.55
     Abp
    -0.55
    Promoting
    -0.53
    idespread
    -0.53
     obsługi
    -0.52
    zzino
    -0.52
    rouge
    -0.51
    POSITIVE LOGITS
     Decide
    1.17
     DECISION
    1.16
    Decide
    1.14
     Decided
    1.13
     decides
    1.11
     deciding
    1.11
     Decisions
    1.11
     decide
    1.11
     decisions
    1.11
     Decision
    1.11
    Activations Density 0.185%

    No Known Activations