© 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. 7615
    Prev
    Next
    INDEX
    Explanations

    references to software patches and updates

    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
    1350
    +0.21
    0.9%
    421
    +0.16
    0.7%
    1328
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.21
    0.02
    421
    +0.16
    0.02
    1194
    +0.13
    0.01
    Negative Logits
     hairc
    -0.72
     linden
    -0.69
     ecru
    -0.67
     Urin
    -0.66
     tupperware
    -0.64
     Alvar
    -0.63
     oleo
    -0.61
     Squal
    -0.61
     resis
    -0.61
     helico
    -0.60
    POSITIVE LOGITS
     patch
    1.48
    patch
    1.40
     Patch
    1.32
     patches
    1.30
    Patch
    1.30
    PATCH
    1.25
    patches
    1.13
     PATCH
    1.11
     patching
    1.10
     patched
    1.02
    Activations Density 0.062%

    No Known Activations