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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13160
    Prev
    Next
    INDEX
    Explanations

    negative descriptors related to conditions or consequences

    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
    AddTagHelper
    -0.82
    SequentialGroup
    -0.75
    IntoConstraints
    -0.74
    ⟬
    -0.73
    rungsseite
    -0.70
     transfieras
    -0.67
    Cyfarwyddwr
    -0.66
     GetEnumerator
    -0.65
    iibo
    -0.65
    OGND
    -0.65
    POSITIVE LOGITS
     Bad
    0.85
     bad
    0.84
    Bad
    0.80
    Worse
    0.77
    Worst
    0.77
     worse
    0.76
     worst
    0.76
     BAD
    0.73
     horrible
    0.72
    worst
    0.71
    Activations Density 0.315%

    No Known Activations