© 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. 31-GEMMASCOPE-RES-16K
    11. 8821
    Prev
    Next
    INDEX
    Explanations

    sentiments related to political discussions and opinions on governance

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

    conditional statements and logical reasoning patterns introduced by words like "if," "then," and "so."

    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
     (;;
    -0.28
    lusconi
    -0.28
    ormány
    -0.28
    tactez
    -0.27
    EnableWeb
    -0.27
    aczy
    -0.26
    どうしても
    -0.26
    蜒
    -0.26
     Remember
    -0.26
     памят
    -0.26
    POSITIVE LOGITS
     fine
    1.45
     OK
    1.30
     great
    1.30
     okay
    1.25
    fine
    1.23
    Fine
    1.23
     ok
    1.22
     wonderful
    1.20
    great
    1.20
     fantastic
    1.19
    Activations Density 0.356%

    No Known Activations