© 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. 287
    Prev
    Next
    INDEX
    Explanations

    content related to innovative technology and its application in various industries

    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
    WriteBarrier
    -0.68
    tagez
    -0.62
    RuleContext
    -0.60
    hObject
    -0.59
     nakalista
    -0.58
     joking
    -0.58
    ^(@)
    -0.55
     Haupt
    -0.54
    detectChanges
    -0.54
    principalColumn
    -0.54
    POSITIVE LOGITS
     sustenance
    0.65
     gamut
    0.64
     marquee
    0.60
     newer
    0.59
     futuristic
    0.56
    Decoding
    0.55
     envisaged
    0.54
     imbib
    0.53
     IPs
    0.53
     domains
    0.53
    Activations Density 0.135%

    No Known Activations