© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1366
    Prev
    Next
    INDEX
    Explanations

    references to military context and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.54
    其中的
    -0.49
     antara
    -0.46
    其中
    -0.42
     ואת
    -0.42
    })));
    -0.41
    between
    -0.41
     obstante
    -0.38
     între
    -0.38
     Gelegenheit
    -0.37
    POSITIVE LOGITS
     standpoint
    1.59
     perspective
    1.51
     onwards
    1.31
     vantage
    1.14
    perspective
    1.14
     perspectives
    1.09
     viewpoint
    1.08
     Perspective
    1.07
    Perspective
    1.01
     onward
    0.98
    Activations Density 0.520%

    No Known Activations