© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5833
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recording" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.80
     بيها
    -0.74
     vache
    -0.73
    ?}",
    -0.72
     JSONException
    -0.66
    ifrance
    -0.66
    Autowired
    -0.65
    SPONSORED
    -0.65
    yargs
    -0.64
    ymmetric
    -0.64
    POSITIVE LOGITS
     recording
    2.84
     Recording
    2.57
     recorded
    2.52
    recording
    2.40
     Recorded
    2.40
     recordings
    2.37
    Recording
    2.36
     RECORDING
    2.35
    recorded
    2.19
    Recorded
    2.15
    Activations Density 0.073%

    No Known Activations