© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14441
    Prev
    Next
    INDEX
    Explanations

    phrases related to sand and dunes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    32
    +0.18
    0.8%
    1222
    +0.17
    0.7%
    1323
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.18
    0.03
    1222
    +0.17
    0.02
    1323
    +0.15
    0.02
    Negative Logits
     Guwahati
    -0.47
     gøre
    -0.45
     tæt
    -0.45
    Initializable
    -0.44
     Utica
    -0.44
     Atiku
    -0.44
     brugt
    -0.43
     Amritsar
    -0.42
     Coimbatore
    -0.42
    Obrázky
    -0.42
    POSITIVE LOGITS
     Sand
    1.48
     sand
    1.47
     SAND
    1.47
    Sand
    1.45
    sand
    1.34
    SAND
    1.29
     sands
    1.19
     Sands
    1.04
     sandbox
    0.98
     Sanderson
    0.96
    Activations Density 0.080%

    No Known Activations