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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65881
    Prev
    Next
    INDEX
    Explanations

    terms related to plant propagation and cultivation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.66
    gebob
    -0.47
    SourceChecksum
    -0.42
    CppMethod
    -0.40
     worms
    -0.40
    Geografie
    -0.39
    depre
    -0.39
    abestanden
    -0.39
    iální
    -0.38
    MigrationBuilder
    -0.38
    POSITIVE LOGITS
     nakalista
    0.64
     culture
    0.60
     Culture
    0.59
    call
    0.57
    Culture
    0.56
     Kultur
    0.54
     Shoot
    0.54
     regener
    0.53
     call
    0.53
     Call
    0.52
    Activations Density 0.032%

    No Known Activations