© 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. 23-GEMMASCOPE-RES-16K
    6. 10145
    Prev
    Next
    INDEX
    Explanations

    references to discussions and decisions regarding outsourcing and organizational changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.68
     صوتيه
    -0.65
     itſelf
    -0.64
     Eſ
    -0.64
     whoſe
    -0.63
     houſe
    -0.62
    ſelf
    -0.61
     himſelf
    -0.60
     pleaſure
    -0.59
     يتيمه
    -0.58
    POSITIVE LOGITS
     considering
    1.27
     consideration
    1.22
     explored
    1.16
     exploring
    1.16
     consider
    1.14
     CONSIDER
    1.13
    considering
    1.07
     explore
    1.06
     contemplating
    1.05
    Consider
    1.04
    Activations Density 0.425%

    No Known Activations