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. 20-GEMMASCOPE-RES-16K
    6. 12852
    Prev
    Next
    INDEX
    Explanations

    relative paths in code or file references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.40
     ujednoznacz
    -0.40
    ConstraintMaker
    -0.39
     OMITBAD
    -0.37
    ativement
    -0.36
    下载附件
    -0.35
     године
    -0.34
    omitempty
    -0.33
    яза
    -0.33
     thức
    -0.33
    POSITIVE LOGITS
     "../../
    1.28
     '../
    1.27
     '../../
    1.26
     "../
    1.25
     '../../../
    1.21
     "../../../../
    1.20
    ="../
    1.15
     "../../../
    1.13
     '../../../../
    1.12
    ('../../../
    1.11
    Activations Density 0.025%

    No Known Activations