© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3814
    Prev
    Next
    INDEX
    Explanations

    programming structures and definitions related to subscriptions and events

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

    Followed by a curly brace and the word "result"

    np_acts-logits-general · gemini-2.0-flash

    local data fields and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     estoppel
    -0.58
    ->___
    -0.57
     recensement
    -0.52
     declaratory
    -0.51
     defensively
    -0.51
     remarquer
    -0.49
     продаж
    -0.47
    ensk
    -0.47
     dimethyl
    -0.47
     hippocampal
    -0.46
    POSITIVE LOGITS
     type
    0.91
     متعلقه
    0.84
     method
    0.79
     action
    0.74
    method
    0.71
     destination
    0.71
    type
    0.71
     Method
    0.70
     Type
    0.70
    ntype
    0.69
    Activations Density 0.605%

    No Known Activations