© 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. 14588
    Prev
    Next
    INDEX
    Explanations

    mentions of feedback, comments, suggestions, pledges, donations, requests, interviews, responses, and complaints in a document

    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
    136
    +0.09
    0.3%
    1870
    +0.08
    0.2%
    86
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.09
    0.04
    1652
    +0.08
    0.05
    1553
    +0.07
    0.06
    Negative Logits
     vogli
    -0.84
     Cfr
    -0.81
     sappi
    -0.80
     télécharge
    -0.79
     Però
    -0.76
     Mentre
    -0.74
     vedo
    -0.74
     Sì
    -0.73
     anzi
    -0.71
     dimenti
    -0.70
    POSITIVE LOGITS
     received
    0.79
     submitted
    0.70
     solicited
    0.68
     collected
    0.67
     recieved
    0.66
     submissions
    0.66
     hurled
    0.62
     emanating
    0.60
     shivered
    0.59
     barked
    0.57
    Activations Density 0.485%

    No Known Activations