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. 22-GEMMASCOPE-RES-16K
    6. 10251
    Prev
    Next
    INDEX
    Explanations

    instances of specific dates, particularly those in July

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

    the month July

    np_acts-logits-general · gemini-2.0-flash

    dates and months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McGuire
    -0.49
    5
    -0.43
    FP
    -0.43
     conta
    -0.43
    9
    -0.43
    PSS
    -0.43
    8
    -0.42
     Reiss
    -0.42
     çek
    -0.42
    fp
    -0.42
    POSITIVE LOGITS
    JULY
    1.08
     JULY
    1.04
    july
    1.03
    July
    0.98
     july
    0.95
     July
    0.94
     صوتيه
    0.88
     juillet
    0.87
    ########.
    0.85
    ">//
    0.84
    Activations Density 0.053%

    No Known Activations