© 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. 37-GEMMASCOPE-RES-16K
    6. 4367
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to pairs and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [['
    -0.51
     [['
    -0.47
    Jeografia
    -0.41
    accompagnement
    -0.41
    FormState
    -0.38
    [_
    -0.38
     desmotivaciones
    -0.37
    amitié
    -0.35
    MemoryWarning
    -0.35
    Tamil
    -0.35
    POSITIVE LOGITS
     $(
    1.84
    $(
    1.63
     }(
    1.41
     }}(
    1.20
    ($(
    1.13
    =$(
    1.12
     ($(
    1.00
    }(
    0.99
    }}(
    0.91
     "$(
    0.91
    Activations Density 1.362%

    No Known Activations