© 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. 8916
    Prev
    Next
    INDEX
    Explanations

    signs of positive experiences and recommendations

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

    first-person pronouns and positive sentiment words in personal reviews and testimonials.

    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
    sizeCache
    -0.59
    WireFormatLite
    -0.56
    EndContext
    -0.56
     resourceCulture
    -0.53
    IBOutlet
    -0.52
    PageContext
    -0.52
    keyColumn
    -0.51
    CPtr
    -0.50
    LLocation
    -0.49
    ########.
    -0.49
    POSITIVE LOGITS
     Highly
    0.99
     highly
    0.93
     Recommended
    0.92
     Recommend
    0.90
     recommend
    0.90
    Highly
    0.88
     worth
    0.85
     recommended
    0.84
     Definitely
    0.81
     Worth
    0.80
    Activations Density 0.102%

    No Known Activations