© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 665
    Prev
    Next
    INDEX
    Explanations

    locations or landmarks in Arkansas

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1265
    +0.11
    0.3%
    553
    +0.11
    0.3%
    789
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.04
    283
    +0.11
    0.01
    1363
    +0.09
    0.03
    Negative Logits
    BeginContext
    -0.61
    <bos>
    -0.57
    </tbody>
    -0.55
     onAnimation
    -0.55
    istoitu
    -0.54
                
    -0.54
    cho
    -0.54
               
    -0.53
    <eos>
    -0.53
     кӀош
    -0.53
    POSITIVE LOGITS
     Ark
    1.96
     ark
    1.85
    Ark
    1.84
    ark
    1.76
     ARK
    1.59
    ARK
    1.50
     jorge
    1.39
     ricardo
    1.35
     Arc
    1.34
     effe
    1.34
    Activations Density 0.259%

    No Known Activations