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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6589
    Prev
    Next
    INDEX
    Explanations

    phrases related to adaptation and flexibility in response to changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joyería
    -0.40
    Hund
    -0.35
     Oppen
    -0.35
    <bos>
    -0.33
     πυ
    -0.33
    IVEREF
    -0.32
    ξύ
    -0.32
     depository
    -0.32
    nalpot
    -0.32
    inigungs
    -0.32
    POSITIVE LOGITS
     adapt
    1.97
     adapts
    1.87
     adaptation
    1.87
     adapting
    1.84
    Adaptation
    1.79
     Adaptation
    1.77
    adapt
    1.77
     adapted
    1.77
     Adapt
    1.76
    adaptation
    1.73
    Activations Density 0.217%

    No Known Activations