© 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. 24-GEMMASCOPE-RES-16K
    11. 5296
    Prev
    Next
    INDEX
    Explanations

    dialogue and interactions between characters expressing emotions and consequences

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

    Exclamations, questions, and imperative statements

    np_acts-logits-general · gemini-2.0-flash

    Okay!!! infiltration capacity 4+ as well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.57
     Apparently
    -0.55
    Apparently
    -0.53
     ujednoznacz
    -0.50
     lenker
    -0.50
    IndentedString
    -0.50
    angelog
    -0.49
     ويكيميديا
    -0.48
    apparently
    -0.48
    ValueStyle
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.42
    trust
    0.41
     trust
    0.41
     promise
    0.39
    Trust
    0.37
     listen
    0.37
     Promise
    0.36
     trusts
    0.35
     reassure
    0.35
     promesse
    0.34
    Activations Density 0.117%

    No Known Activations