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. 23-GEMMASCOPE-RES-16K
    6. 9308
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing processes and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions of edges or borders of materials/objects, especially their shape/condition and operations done to them (e.g., trimming, folding, joining).

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     nahilalakip
    -0.69
    RegressionTest
    -0.48
    figsize
    -0.46
    SEQUENCE
    -0.45
    modelBuilder
    -0.45
    Enigma
    -0.45
     Allociné
    -0.44
    parsedMessage
    -0.44
    твер
    -0.44
     Preferencias
    -0.43
    POSITIVE LOGITS
     edges
    1.48
     edge
    1.39
     Edges
    1.20
     corners
    1.15
    edges
    1.15
    edge
    1.07
    Edge
    1.02
     corner
    1.01
     Edge
    1.01
    Edges
    1.00
    Activations Density 0.509%

    No Known Activations