Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3274
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming and data management

    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
    PhysRev
    -0.59
    bootstrapcdn
    -0.54
     kasarigan
    -0.48
     PARTICULAR
    -0.46
    Eloquent
    -0.44
    AnimationsModule
    -0.42
    </thead>
    -0.42
    casted
    -0.42
    boli
    -0.42
    Arrived
    -0.41
    POSITIVE LOGITS
    InputBorder
    0.63
    ustom
    0.62
    entral
    0.60
    heck
    0.58
    urrent
    0.57
    ivil
    0.57
    lose
    0.56
    ycle
    0.56
    enter
    0.56
    luster
    0.56
    Activations Density 0.465%

    No Known Activations