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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9203
    Prev
    Next
    INDEX
    Explanations

    references to television show elements, particularly title sequences and sound effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.70
     CreateTagHelper
    -0.70
    BeginInit
    -0.63
    ništvo
    -0.61
     صوتيه
    -0.57
    TargetException
    -0.54
    UrlResolution
    -0.50
    SequentialGroup
    -0.50
     الاطلاع
    -0.49
    FunctionFlags
    -0.49
    POSITIVE LOGITS
     Season
    1.84
     season
    1.80
     episode
    1.79
     episodes
    1.70
    Season
    1.65
     series
    1.53
     Episode
    1.53
    season
    1.53
    episode
    1.48
     Episodes
    1.41
    Activations Density 0.506%

    No Known Activations