© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 809
    Prev
    Next
    INDEX
    Explanations

    queries about problem-solving or asking for assistance with technical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourself
    -0.63
    enderror
    -0.60
    __*/
    -0.60
    Удачи
    -0.55
     YOURSELF
    -0.55
    yourself
    -0.53
    śmie
    -0.53
    TextWatcher
    -0.52
     Roskov
    -0.52
    Yourself
    -0.52
    POSITIVE LOGITS
     Any
    1.25
     Anyone
    1.24
     anyone
    1.22
    Any
    1.21
    Anyone
    1.19
     Anybody
    1.17
     any
    1.14
     anybody
    1.10
     HELP
    1.10
    anyone
    1.08
    Activations Density 0.528%

    No Known Activations