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. 12-GEMMASCOPE-RES-16K
    6. 2653
    Prev
    Next
    INDEX
    Explanations

    terms related to iron and its biological significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the neuron detects numeric measurements or numbers appearing as part of numeric ranges (tokens involved in values with hyphens/minus signs).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poire
    -0.48
    Vendo
    -0.43
    сама
    -0.41
    Useless
    -0.41
    inner
    -0.41
     gran
    -0.40
     onBind
    -0.39
    jeras
    -0.39
    circular
    -0.39
     myš
    -0.38
    POSITIVE LOGITS
    ]")]
    0.85
    AnchorStyles
    0.80
    EndContext
    0.77
     оригіналу
    0.74
    RectangleBorder
    0.73
    abestanden
    0.72
    parsedMessage
    0.70
     تضيفلها
    0.65
     OFDb
    0.65
     OnTrigger
    0.64
    Activations Density 1.084%

    No Known Activations