© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14835
    Prev
    Next
    INDEX
    Explanations

    mentions of geological features and characteristics

    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
    1577
    +0.51
    2.0%
    50
    +0.22
    0.8%
    381
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.51
    0.20
    184
    +0.22
    0.07
    1965
    +0.11
    0.10
    Negative Logits
     mercen
    -0.55
     churrasco
    -0.52
     Darío
    -0.49
     Áng
    -0.47
     Mónica
    -0.47
     curé
    -0.46
    membrance
    -0.46
     tortas
    -0.46
     paillettes
    -0.45
    calciatore
    -0.45
    POSITIVE LOGITS
     inoltre
    0.65
     furthermore
    0.50
     Expt
    0.47
     however
    0.46
     aen
    0.46
     moreover
    0.45
     !'
    0.45
    :,,
    0.44
     also
    0.44
    ouncil
    0.44
    Activations Density 3.871%

    No Known Activations