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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7484
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bewußt
    -0.52
    ,
    -0.49
     lisäksi
    -0.48
     Erwachsenen
    -0.44
     because
    -0.44
    jalá
    -0.42
     but
    -0.42
     Sünde
    -0.42
     Geburt
    -0.42
     Constitucional
    -0.42
    POSITIVE LOGITS
    .\\
    0.58
    ."""
    0.57
     defStyle
    0.54
    .
    
    0.54
    OGND
    0.53
     Normdatei
    0.52
     nakalista
    0.52
     AssemblyCulture
    0.51
    .
    0.50
     _:
    0.50
    Activations Density 4.152%

    No Known Activations