© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    evidence and claims related to specific events, particularly in a legal or investigative context

    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
    mapStateToProps
    -0.63
    dür
    -0.52
    qtype
    -0.50
     springfox
    -0.49
    FormTagHelper
    -0.49
    codegen
    -0.48
    ngrx
    -0.48
    actylus
    -0.48
    ikbaar
    -0.46
     EconPapers
    -0.46
    POSITIVE LOGITS
     refute
    1.43
     refuted
    1.37
     disprove
    1.36
     deb
    1.34
     rebuttal
    1.24
     dispel
    1.22
     rebut
    1.21
     contradicted
    1.07
     опро
    1.04
     disp
    1.04
    Activations Density 0.650%

    No Known Activations